Rohit Pillai – Medium

Rohit Pillai

Rohit Pillai
in
Towards Data Science

CODIR: Train smaller, faster NLP models

A unique approach to knowledge distillation

Jan 4, 2021

CODIR: Train smaller, faster NLP models

Jan 4, 2021

Rohit Pillai
in
Towards Data Science

SpanFact: Fix your factually incorrect summaries

A suite of models that fixes inaccuracies in summaries of large text

Dec 16, 2020

SpanFact: Fix your factually incorrect summaries

Dec 16, 2020

Rohit Pillai
in
Towards Data Science

HERO: You’ll never have to watch long videos again

A model that understands a video and its subtitles to help you speed through it

Sep 17, 2020

HERO: You’ll never have to watch long videos again

Sep 17, 2020

Rohit Pillai
in
The Startup

FILTER: Understand Foreign Languages Better

A technique that promotes a deeper understanding and linkage between the same text in different languages

Sep 16, 2020

FILTER: Understand Foreign Languages Better

Sep 16, 2020

Rohit Pillai
in
Towards Data Science

DiscoBERT: A BERT that shortens your reading time

A Discourse Aware BERT that improves summary generation

Aug 22, 2020

DiscoBERT: A BERT that shortens your reading time

Aug 22, 2020

Rohit Pillai
in
The Startup

Distill-BERT: Using BERT for Smarter Text Generation

Generate better stories, essays, answers and more using BERT’s knowledge

Aug 7, 2020

Distill-BERT: Using BERT for Smarter Text Generation

Aug 7, 2020

Rohit Pillai
in
Towards Data Science

VILLA: A Generic Adversarial Training technique for Vision-and-Language

The first multimodal adversarial training technique for image and text models

Jul 13, 2020

VILLA: A Generic Adversarial Training technique for Vision-and-Language

Jul 13, 2020

Rohit Pillai
in
The Startup

BachGAN: Let your imagination run free

Create real images with just boxes!

May 15, 2020

BachGAN: Let your imagination run free

May 15, 2020

Rohit Pillai
in
The Startup

VIOLIN: Do you really understand videos?

A new task and dataset that requires multi-modal understanding of videos and text

May 3, 2020

VIOLIN: Do you really understand videos?

May 3, 2020

Rohit Pillai
in
Towards Data Science

UNITER

Learning a joint representation of image and text that everything can use

Mar 5, 2020

UNITER

Mar 5, 2020

Rohit Pillai

Rohit Pillai

I’m an engineer at Microsoft Dynamics 365 AI Research and I’ll post our new NLP, CV and Multimodal research . Check out https://medium.com/@rohit.rameshp

Help
Status
About
Careers
Press
Blog
Privacy
Terms
Text to speech
Teams